npm - @futuretea/rancher-mcp-server - Versions diffs - 0.3.3 → 0.4.0 - Mend

@futuretea/rancher-mcp-server 0.3.3 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (2) hide show

package/README.md +227 -251
package/package.json +7 -7

package/README.md CHANGED Viewed

@@ -4,38 +4,31 @@
 [![npm](https://img.shields.io/npm/v/@futuretea/rancher-mcp-server)](https://www.npmjs.com/package/@futuretea/rancher-mcp-server)
 [![GitHub release (latest SemVer)](https://img.shields.io/github/v/release/futuretea/rancher-mcp-server?sort=semver)](https://github.com/futuretea/rancher-mcp-server/releases/latest)
-[✨ Features](#features) | [🚀 Getting Started](#getting-started) | [⚙️ Configuration](#configuration) | [🛠️ Tools](#tools-and-functionalities) | [🧑‍💻 Development](#development)
-## ✨ Features <a id="features"></a>
-A powerful and flexible [Model Context Protocol (MCP)](https://blog.marcnuri.com/model-context-protocol-mcp-introduction) server implementation with support for **Rancher multi-cluster management**.
-- **✅ Multi-cluster Management**: Access and manage multiple Kubernetes clusters through Rancher API
-- **✅ Core Kubernetes Resources**: Perform operations on Kubernetes resources across multiple clusters
-  - **List** clusters, nodes, workloads, namespaces, services, configmaps, and secrets
-  - **Get** kubeconfig for any cluster
-  - **Intelligent Diagnostic Chain**: Perform health checks with Service → Pods and Ingress → Service → Pods diagnostic chains
-  - **Ready/Degraded Dual-State Diagnosis**: Identify both critical failures and performance degradation
-- **✅ Rancher-specific Resources**: Access Rancher-specific resources
-  - **List** Rancher projects and users
-  - **Check** cluster health status
-  - **View** project access permissions
-- **✅ Security Configuration**: Support for read-only mode and disabling destructive operations
-  - **Secrets Protection**: Secret data is never exposed, only metadata
-- **✅ Multiple Output Formats**: Support for table, YAML, and JSON output formats
-- **✅ Performance Optimized**: Intelligent API call caching reduces API calls by up to 93% during bulk operations
-- **✅ Cross-platform Support**: Available as native binaries for Linux, macOS, and Windows, as well as an npm package
-Unlike other Kubernetes MCP server implementations, this server is **specifically designed for Rancher multi-cluster environments** and provides seamless access to multiple clusters through a single interface.
-- **✅ Lightweight**: The server is distributed as a single native binary for Linux, macOS, and Windows
-- **✅ High-Performance / Low-Latency**: Directly interacts with Rancher API server without the overhead of calling external commands
-- **✅ Efficient Bulk Operations**: Optimized API calls with intelligent caching for diagnosing multiple resources
-- **✅ Self-Documenting**: Detailed tool descriptions help LLMs understand capabilities and select the right tools
-- **✅ Configurable**: Supports [command-line arguments](#configuration) to configure the server behavior
-- **✅ Well tested**: The server has an extensive test suite to ensure its reliability and correctness
-## 🚀 Getting Started <a id="getting-started"></a>
+[Features](#features) | [Getting Started](#getting-started) | [Configuration](#configuration) | [Tools](#tools-and-functionalities) | [Development](#development)
+## Features <a id="features"></a>
+A [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for Rancher multi-cluster management.
+- **Multi-cluster Management**: Access multiple Kubernetes clusters through Rancher API
+- **Kubernetes Resources via Steve API**: CRUD operations on any resource type
+  - Get/List any resource (Pod, Deployment, Service, ConfigMap, Secret, CRD, etc.)
+  - Create resources from JSON manifests
+  - Patch resources using JSON Patch (RFC 6902)
+  - Delete resources
+  - Query container logs with filtering (tail lines, time range, timestamps)
+  - Inspect pods with parent workload, metrics, and logs
+- **Rancher Resources via Norman API**: List clusters and projects
+- **Security Controls**:
+  - `read_only`: Disables create, patch, and delete operations
+  - `disable_destructive`: Disables delete operations only
+  - Secret data is never exposed, only metadata
+- **Output Formats**: Table, YAML, and JSON
+- **Output Filters**: Remove verbose fields like `managedFields` from responses
+- **Pagination**: Limit and page parameters for list operations
+- **Cross-platform**: Native binaries for Linux, macOS, Windows, and npm package
+## Getting Started <a id="getting-started"></a>
 ### Requirements
@@ -44,11 +37,7 @@ Unlike other Kubernetes MCP server implementations, this server is **specificall
 ### Claude Desktop
-#### Using npx
-If you have npm installed, this is the fastest way to get started with `@futuretea/rancher-mcp-server` on Claude Desktop.
-Open your `claude_desktop_config.json` and add the mcp server to the list of `mcpServers`:
+Using npx:
 ```json
 {
@@ -59,7 +48,7 @@ Open your `claude_desktop_config.json` and add the mcp server to the list of `mc
         "-y",
         "@futuretea/rancher-mcp-server@latest",
         "--rancher-server-url",
-        "https://your-rancher-server.com/v3",
+        "https://your-rancher-server.com",
         "--rancher-token",
         "your-token"
       ]
@@ -70,19 +59,17 @@ Open your `claude_desktop_config.json` and add the mcp server to the list of `mc
 ### VS Code / VS Code Insiders
-Install the Rancher MCP server extension in VS Code by running the following command:
 ```shell
 # For VS Code
-code --add-mcp '{"name":"rancher","command":"npx","args":["@futuretea/rancher-mcp-server@latest","--rancher-server-url","https://your-rancher-server.com/v3","--rancher-token","your-token"]}'
+code --add-mcp '{"name":"rancher","command":"npx","args":["@futuretea/rancher-mcp-server@latest","--rancher-server-url","https://your-rancher-server.com","--rancher-token","your-token"]}'
 # For VS Code Insiders
-code-insiders --add-mcp '{"name":"rancher","command":"npx","args":["@futuretea/rancher-mcp-server@latest","--rancher-server-url","https://your-rancher-server.com/v3","--rancher-token","your-token"]}'
+code-insiders --add-mcp '{"name":"rancher","command":"npx","args":["@futuretea/rancher-mcp-server@latest","--rancher-server-url","https://your-rancher-server.com","--rancher-token","your-token"]}'
 ```
 ### Cursor
-Install the Rancher MCP server extension in Cursor by editing the `mcp.json` file:
+Edit `mcp.json`:
 ```json
 {
@@ -93,7 +80,7 @@ Install the Rancher MCP server extension in Cursor by editing the `mcp.json` fil
         "-y",
         "@futuretea/rancher-mcp-server@latest",
         "--rancher-server-url",
-        "https://your-rancher-server.com/v3",
+        "https://your-rancher-server.com",
         "--rancher-token",
         "your-token"
       ]
@@ -102,296 +89,285 @@ Install the Rancher MCP server extension in Cursor by editing the `mcp.json` fil
 }
 ```
-## ⚙️ Configuration <a id="configuration"></a>
+## Configuration <a id="configuration"></a>
-The Rancher MCP server can be configured using command line (CLI) arguments or a configuration file.
+Configuration can be set via CLI flags, environment variables, or a config file.
-You can run the CLI executable either by using `npx` or by downloading the [latest release binary](https://github.com/futuretea/rancher-mcp-server/releases/latest).
+**Priority (highest to lowest):**
+1. Command-line flags
+2. Environment variables (prefix: `RANCHER_MCP_`)
+3. Configuration file
+4. Default values
-```shell
-# Run the Rancher MCP server using npx (in case you have npm and node installed)
-npx @futuretea/rancher-mcp-server@latest --help
-```
+### CLI Options
 ```shell
-# Run the Rancher MCP server using the latest release binary
-./rancher-mcp-server --help
+npx @futuretea/rancher-mcp-server@latest --help
 ```
-### Configuration Options
-| Option | Description |
-|--------|-------------|
-| `--port` | Starts the MCP server in HTTP/SSE mode and listens on the specified port. Use 0 for stdio mode (default for MCP clients) |
-| `--sse-base-url` | SSE public base URL to use when sending the endpoint message (e.g. https://example.com) |
-| `--log-level` | Sets the logging level (values from 0-9) |
-| `--rancher-server-url` | URL of the Rancher server (must include `/v3` path, e.g., `https://your-rancher-server.com/v3`) |
-| `--rancher-token` | Bearer token for Rancher API authentication |
-| `--rancher-access-key` | Access key for Rancher API authentication |
-| `--rancher-secret-key` | Secret key for Rancher API authentication |
-| `--rancher-tls-insecure` | Skip TLS certificate verification for Rancher server (default: false) |
-| `--list-output` | Output format for resource list operations (one of: table, yaml, json) (default "json") |
-| `--read-only` | If set, the MCP server will run in read-only mode, meaning it will not allow any write operations on the Rancher cluster |
-| `--disable-destructive` | If set, the MCP server will disable all destructive operations on the Rancher cluster |
-| `--toolsets` | Comma-separated list of toolsets to enable. Default: [config,core,rancher,networking] |
-| `--enabled-tools` | Comma-separated list of tools to enable (overrides toolsets) |
-| `--disabled-tools` | Comma-separated list of tools to disable (overrides toolsets) |
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--config` | Config file path (YAML) | |
+| `--port` | Port for HTTP/SSE mode (0 = stdio mode) | `0` |
+| `--sse-base-url` | Public base URL for SSE endpoint | |
+| `--log-level` | Log level (0-9) | `0` |
+| `--rancher-server-url` | Rancher server URL | |
+| `--rancher-token` | Rancher bearer token | |
+| `--rancher-access-key` | Rancher access key | |
+| `--rancher-secret-key` | Rancher secret key | |
+| `--rancher-tls-insecure` | Skip TLS verification | `false` |
+| `--read-only` | Disable write operations | `true` |
+| `--disable-destructive` | Disable delete operations | `false` |
+| `--list-output` | Output format (json, table, yaml) | `json` |
+| `--output-filters` | Fields to remove from output | `metadata.managedFields` |
+| `--toolsets` | Toolsets to enable | `kubernetes,rancher` |
+| `--enabled-tools` | Specific tools to enable | |
+| `--disabled-tools` | Specific tools to disable | |
 ### Configuration File
-Create a configuration file `config.yaml`:
+Create `config.yaml`:
 ```yaml
-port: 0  # 0 for stdio mode, set to a port number (e.g., 8080) for HTTP/SSE mode
-log_level: 0
+port: 0  # 0 for stdio, or set a port like 8080 for HTTP/SSE
-# SSE (Server-Sent Events) configuration (optional, for HTTP/SSE mode)
-# sse_base_url: https://your-domain.com:8080
+log_level: 0
-rancher_server_url: https://your-rancher-server.com/v3
+rancher_server_url: https://your-rancher-server.com
 rancher_token: your-bearer-token
 # Or use Access Key/Secret Key:
 # rancher_access_key: your-access-key
 # rancher_secret_key: your-secret-key
-list_output: json
-read_only: false
+# rancher_tls_insecure: false
+read_only: true  # default: true
 disable_destructive: false
+list_output: json
+# Remove verbose fields from output
+output_filters:
+  - metadata.managedFields
+  - metadata.annotations.kubectl.kubernetes.io/last-applied-configuration
 toolsets:
-  - config
-  - core
+  - kubernetes
   - rancher
-  - networking  # Optional: enable network resource management
+# enabled_tools: []
+# disabled_tools: []
 ```
-### HTTP/SSE Mode
+### Environment Variables
-The Rancher MCP server supports running in HTTP/SSE (Server-Sent Events) mode for network-based access. This is useful when you want to:
+Use `RANCHER_MCP_` prefix with underscores:
-- Access the server from remote clients
-- Use the server in a containerized environment
-- Enable multiple clients to connect to the same server instance
+```shell
+RANCHER_MCP_PORT=8080
+RANCHER_MCP_RANCHER_SERVER_URL=https://rancher.example.com
+RANCHER_MCP_RANCHER_TOKEN=your-token
+RANCHER_MCP_READ_ONLY=true
+```
-#### Running in HTTP/SSE Mode
+### HTTP/SSE Mode
+Run with a port number for network access:
 ```shell
-# Start the server on port 8080
 rancher-mcp-server --port 8080 \
-  --rancher-server-url https://your-rancher-server.com/v3 \
+  --rancher-server-url https://your-rancher-server.com \
   --rancher-token your-token
 ```
-The server will expose the following endpoints:
-- **`/healthz`** - Health check endpoint (returns 200 OK)
-- **`/mcp`** - Streamable HTTP endpoint for MCP protocol
-- **`/sse`** - Server-Sent Events endpoint for real-time communication
-- **`/message`** - Message endpoint for SSE clients
+Endpoints:
+- `/healthz` - Health check
+- `/mcp` - Streamable HTTP endpoint
+- `/sse` - Server-Sent Events endpoint
+- `/message` - Message endpoint for SSE clients
-#### Using SSE Base URL
-When deploying behind a reverse proxy or load balancer, you can specify a public base URL:
+With a public URL behind a proxy:
 ```shell
 rancher-mcp-server --port 8080 \
   --sse-base-url https://your-domain.com:8080 \
-  --rancher-server-url https://your-rancher-server.com/v3 \
+  --rancher-server-url https://your-rancher-server.com \
   --rancher-token your-token
 ```
-## 🛠️ Tools and Functionalities <a id="tools-and-functionalities"></a>
+## Tools and Functionalities <a id="tools-and-functionalities"></a>
+Tools are organized into toolsets. Use `--toolsets` to enable specific sets or `--enabled-tools`/`--disabled-tools` for fine-grained control.
+### Toolsets
+| Toolset | API | Description |
+|---------|-----|-------------|
+| kubernetes | Steve | Kubernetes CRUD operations for any resource type |
+| rancher | Norman | Cluster and project listing |
+### kubernetes
+<details>
+<summary>kubernetes_get</summary>
+Get a Kubernetes resource by kind, namespace, and name.
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `kind` | string | Yes | Resource kind (e.g., pod, deployment, service) |
+| `namespace` | string | No | Namespace (optional for cluster-scoped resources) |
+| `name` | string | Yes | Resource name |
+| `format` | string | No | Output format: json, yaml (default: json) |
-The Rancher MCP server supports enabling or disabling specific groups of tools and functionalities (toolsets) via the `--toolsets` command-line flag or `toolsets` configuration option.
-This allows you to control which Rancher functionalities are available to your AI tools.
-Enabling only the toolsets you need can help reduce the context size and improve the LLM's tool selection accuracy.
+</details>
-### Available Toolsets
+<details>
+<summary>kubernetes_list</summary>
-The following sets of tools are available (all on by default):
+List Kubernetes resources by kind.
-| Toolset | Description |
-|---------|-------------|
-| config | Tools for managing cluster configuration (kubeconfig) |
-| core | Core Kubernetes resource management tools (nodes, workloads, namespaces, configmaps, secrets, services) |
-| rancher | Rancher-specific tools (clusters, projects, users, cluster health, access control) |
-| networking | Network resource management tools (ingresses) |
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `kind` | string | Yes | Resource kind |
+| `namespace` | string | No | Namespace (empty = all namespaces) |
+| `name` | string | No | Filter by name (partial match) |
+| `labelSelector` | string | No | Label selector (e.g., "app=nginx,env=prod") |
+| `limit` | integer | No | Items per page (default: 100) |
+| `page` | integer | No | Page number, starting from 1 (default: 1) |
+| `format` | string | No | Output format: json, table, yaml (default: json) |
-### Tools
+</details>
 <details>
-<summary>config</summary>
+<summary>kubernetes_logs</summary>
+Get logs from a pod container.
-- **configuration_view** - Generate and view Kubernetes configuration (kubeconfig) for a Rancher cluster
-  - `cluster` (`string`) - Cluster ID to generate kubeconfig for
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `namespace` | string | Yes | Namespace |
+| `name` | string | Yes | Pod name |
+| `container` | string | No | Container name (empty = all containers) |
+| `tailLines` | integer | No | Lines from end (default: 100) |
+| `sinceSeconds` | integer | No | Logs from last N seconds |
+| `timestamps` | boolean | No | Include timestamps (default: false) |
+| `previous` | boolean | No | Previous container instance (default: false) |
 </details>
 <details>
-<summary>core</summary>
-- **cluster_list** - List all available Kubernetes clusters
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **node_get** - Get a single node by ID, more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `node` (`string`) **(required)** - Node ID to get
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **node_list** - List all nodes in a cluster
-  - `cluster` (`string`) - Cluster ID to list nodes from (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **workload_get** - Get a single workload by name and namespace, more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `namespace` (`string`) **(required)** - Namespace name
-  - `name` (`string`) **(required)** - Workload name to get
-  - `project` (`string`) - Project ID (optional, will auto-detect if not provided)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **workload_list** - List workloads (deployments, statefulsets, daemonsets, jobs) and orphan pods in a cluster
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter workloads (optional)
-  - `namespace` (`string`) - Namespace name to filter workloads (optional)
-  - `node` (`string`) - Node name to filter workloads (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **namespace_get** - Get a single namespace by name, more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `name` (`string`) **(required)** - Namespace name to get
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **namespace_list** - List namespaces in a cluster
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter namespaces (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **configmap_get** - Get a single ConfigMap by name and namespace, more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `namespace` (`string`) **(required)** - Namespace name
-  - `name` (`string`) **(required)** - ConfigMap name to get
-  - `project` (`string`) - Project ID (optional, will auto-detect if not provided)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **configmap_list** - List all ConfigMaps in a cluster
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter ConfigMaps (optional)
-  - `namespace` (`string`) - Namespace name to filter ConfigMaps (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **secret_get** - Get a single Secret by name and namespace, more efficient than list (metadata only, does not expose secret data)
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `namespace` (`string`) **(required)** - Namespace name
-  - `name` (`string`) **(required)** - Secret name to get
-  - `project` (`string`) - Project ID (optional, will auto-detect if not provided)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **secret_list** - List all Secrets in a cluster (metadata only, does not expose secret data)
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter secrets (optional)
-  - `namespace` (`string`) - Namespace name to filter secrets (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
-- **service_get** - Get a single service by name with optional pod diagnostic check (Service → Pods), more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `namespace` (`string`) **(required)** - Namespace name
-  - `name` (`string`) **(required)** - Service name to get
-  - `project` (`string`) - Project ID (optional, will auto-detect if not provided)
-  - `getPodDetails` (`boolean`) - Get detailed pod information and perform health checks (default: false)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **service_list** - List services with optional pod diagnostic check (Service → Pods)
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter services (optional)
-  - `namespace` (`string`) - Namespace name to filter services (optional)
-  - `getPodDetails` (`boolean`) - Get pod information and perform health checks for services (default: false)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+<summary>kubernetes_inspect_pod</summary>
+Get pod diagnostics: details, parent workload, metrics, and logs.
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `namespace` | string | Yes | Namespace |
+| `name` | string | Yes | Pod name |
 </details>
 <details>
-<summary>rancher</summary>
+<summary>kubernetes_create</summary>
-- **cluster_list** - List all available Kubernetes clusters
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+Create a Kubernetes resource. Disabled when `read_only=true`.
-- **project_get** - Get a single Rancher project by ID, more efficient than list
-  - `project` (`string`) **(required)** - Project ID to get
-  - `cluster` (`string`) **(required)** - Cluster ID (required for verification)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `resource` | string | Yes | JSON manifest (must include apiVersion, kind, metadata, spec) |
-- **project_list** - List Rancher projects across clusters
-  - `cluster` (`string`) - Filter projects by cluster ID (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+</details>
+<details>
+<summary>kubernetes_patch</summary>
+Patch a resource using JSON Patch (RFC 6902). Disabled when `read_only=true`.
-- **user_get** - Get a single Rancher user by ID, more efficient than list
-  - `user` (`string`) **(required)** - User ID to get
-  - `format` (`string`) - Output format: yaml or json (default: "json")
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `kind` | string | Yes | Resource kind |
+| `namespace` | string | No | Namespace (optional for cluster-scoped) |
+| `name` | string | Yes | Resource name |
+| `patch` | string | Yes | JSON Patch array, e.g., `[{"op":"replace","path":"/spec/replicas","value":3}]` |
-- **user_list** - List all Rancher users
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+</details>
+<details>
+<summary>kubernetes_delete</summary>
-- **cluster_health** - Get health status of Rancher clusters
-  - `cluster` (`string`) - Specific cluster ID to check health (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+Delete a Kubernetes resource. Disabled when `read_only=true` or `disable_destructive=true`.
-- **project_access** - List user access permissions for Rancher projects
-  - `project` (`string`) - Project ID to check access (optional)
-  - `cluster` (`string`) - Cluster ID (optional)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | Yes | Cluster ID |
+| `kind` | string | Yes | Resource kind |
+| `namespace` | string | No | Namespace (optional for cluster-scoped) |
+| `name` | string | Yes | Resource name |
 </details>
+### rancher
 <details>
-<summary>networking</summary>
-- **ingress_get** - Get a single ingress by name with diagnostic chain check (Ingress → Service → Pods), more efficient than list
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `namespace` (`string`) **(required)** - Namespace name
-  - `name` (`string`) **(required)** - Ingress name to get
-  - `project` (`string`) - Project ID (optional, will auto-detect if not provided)
-  - `getPodDetails` (`boolean`) - Get detailed pod information and perform health checks (default: false)
-  - `format` (`string`) - Output format: yaml or json (default: "json")
-- **ingress_list** - List ingresses with full diagnostic chain check (Ingress → Service → Pods)
-  - `cluster` (`string`) **(required)** - Cluster ID
-  - `project` (`string`) - Project ID to filter ingresses (optional)
-  - `namespace` (`string`) - Namespace name to filter ingresses (optional)
-  - `getPodDetails` (`boolean`) - Get detailed pod information and perform health checks (default: false)
-  - `format` (`string`) - Output format: table, yaml, or json (default: "json")
+<summary>cluster_list</summary>
+List available Rancher clusters.
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `name` | string | No | Filter by cluster name (partial match) |
+| `limit` | integer | No | Items per page (default: 100) |
+| `page` | integer | No | Page number (default: 1) |
+| `format` | string | No | Output format: json, table, yaml (default: json) |
 </details>
-## 🧑‍💻 Development <a id="development"></a>
+<details>
+<summary>project_list</summary>
+List Rancher projects.
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `cluster` | string | No | Filter by cluster ID |
+| `name` | string | No | Filter by project name (partial match) |
+| `limit` | integer | No | Items per page (default: 100) |
+| `page` | integer | No | Page number (default: 1) |
+| `format` | string | No | Output format: json, table, yaml (default: json) |
+</details>
-### Running with mcp-inspector
+## Development <a id="development"></a>
-Compile the project and run the Rancher MCP server with [mcp-inspector](https://modelcontextprotocol.io/docs/tools/inspector) to inspect the MCP server.
+### Build
 ```shell
-# Compile the project
 make build
-# Run the Rancher MCP server with mcp-inspector
-npx @modelcontextprotocol/inspector@latest $(pwd)/rancher-mcp-server
 ```
-For more development information, see [DEVELOPMENT.md](DEVELOPMENT.md).
+### Run with mcp-inspector
-## Contributing
+```shell
+npx @modelcontextprotocol/inspector@latest $(pwd)/rancher-mcp-server
+```
-We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details on how to submit issues, feature requests, and pull requests.
+See [DEVELOPMENT.md](DEVELOPMENT.md) for more details.
-### Development
+## Contributing
-For development setup and guidelines, see [DEVELOPMENT.md](DEVELOPMENT.md).
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 ## Support
-If you encounter issues:
-- Create a [GitHub Issue](https://github.com/futuretea/rancher-mcp-server/issues)
-- Check the [troubleshooting guide](TROUBLESHOOTING.md)
-- Review the [documentation](https://github.com/futuretea/rancher-mcp-server/docs)
+- [GitHub Issues](https://github.com/futuretea/rancher-mcp-server/issues)
+- [Troubleshooting Guide](TROUBLESHOOTING.md)
-## Community
+## License
-- **GitHub**: [futuretea/rancher-mcp-server](https://github.com/futuretea/rancher-mcp-server)
-- **Issues**: [GitHub Issues](https://github.com/futuretea/rancher-mcp-server/issues)
-- **Discussions**: [GitHub Discussions](https://github.com/futuretea/rancher-mcp-server/discussions)
+[Apache-2.0](LICENSE)

package/package.json CHANGED Viewed

@@ -1,18 +1,18 @@
 {
   "name": "@futuretea/rancher-mcp-server",
-  "version": "0.3.3",
+  "version": "0.4.0",
   "description": "Model Context Protocol (MCP) server for Rancher multi-cluster management",
   "main": "./bin/index.js",
   "bin": {
     "rancher-mcp-server": "bin/index.js"
   },
   "optionalDependencies": {
-    "@futuretea/rancher-mcp-server-darwin-amd64": "0.3.3",
-    "@futuretea/rancher-mcp-server-darwin-arm64": "0.3.3",
-    "@futuretea/rancher-mcp-server-linux-amd64": "0.3.3",
-    "@futuretea/rancher-mcp-server-linux-arm64": "0.3.3",
-    "@futuretea/rancher-mcp-server-windows-amd64": "0.3.3",
-    "@futuretea/rancher-mcp-server-windows-arm64": "0.3.3"
+    "@futuretea/rancher-mcp-server-darwin-amd64": "0.4.0",
+    "@futuretea/rancher-mcp-server-darwin-arm64": "0.4.0",
+    "@futuretea/rancher-mcp-server-linux-amd64": "0.4.0",
+    "@futuretea/rancher-mcp-server-linux-arm64": "0.4.0",
+    "@futuretea/rancher-mcp-server-windows-amd64": "0.4.0",
+    "@futuretea/rancher-mcp-server-windows-arm64": "0.4.0"
   },
   "repository": {
     "type": "git",